A Further Research On Artificial Intelligence - Deep Learning

The main concept indeeplearning algorithms is automating the extraction of representations (abstractions) from the data.Deep learningalgorithms use a huge amount of unsupervised data to automatically extract complex representation. These algorithms are largely motivated by the field of artificial intelligence, which has the general goal of emulating the human brain’s ability to observe, analyze,learn, and make decisions, especially for extremely complex problems.

Work pertaining to these complex challenges has been a key motivation behindDeep Learningalgorithms which strive to emulate the hierarchicallearningapproach of the human brain. Models based on shallowlearningarchitectures such as decision trees, support vector machines, and case-based reasoning may fall short when attempting to extract useful information from complex structures and relationships in the input corpus. In contrast,Deep Learningarchitectures have the capability to generalize in non-local and global ways, generatinglearningpatterns and relationships beyond immediate neighbors in the data.Deep learningis in fact an important step toward artificial intelligence. It not only provides complex representations of data which are suitable for AI tasks but also makes the machines independent of human knowledge which is the ultimate goal of AI. It extracts representations directly from unsupervised data without human interference.

A key concept underlyingDeep Learningmethods is distributed representations of the data,in which a large number of possible configurations of the abstract features of the input data are feasible, allowing for a compact representation of each sample and leading to a richer generalization.The number of possible configurations is exponentially related to the number of extracted abstract features. Noting that the observed data was generated through interactions of several known/unknown factors, and thus when a data pattern is obtained through some configurations of learnt factors, additional (unseen) data patterns can likely be described through new configurations of the learnt factors and patterns. Compared tolearning based on local generalizations, the number of patterns that can be obtained using a distributed representation scales quickly with the number of learnt factors.

Deep learningalgorithms lead to abstract representations because more abstract representations are often constructed based on less abstract ones.An important advantage of more abstract representations is that they can be invariant to the local changes in the input data.Learningsuch invariant features is an ongoing major goal in pattern recognition (for examplelearningfeatures that are invariant to the face orientation in a face recognition task). Beyond being invariant such representations can also disentangle the factors of variation in data. The real data used in AI-related tasks mostly arise from complicated interactions of many sources. For example an image is composed of different sources of variations such a light, object shapes, and object materials. The abstract representations provided bydeep learningalgorithms can separate the different sources of variations in data.

Deep learningalgorithms are actuallyDeeparchitectures of consecutive layers.Each layer applies a nonlinear transformation on its input and provides a representation in its output. The objective is tolearna complicated and abstract representation of the data in a hierarchical manner by passing the data through multiple transformation layers. The sensory data (for example pixels in an image) is fed to the first layer. Consequently the output of each layer is provided as input to its next layer.

Stacking up the nonlinear transformation layers is the basic idea indeep learningalgorithms. The more layers the data goes through in thedeeparchitecture, the more complicated the nonlinear transformations which are constructed. These transformations represent the data, soDeep Learningcan be considered as special case of representationlearningalgorithms whichlearnrepresentations of the data in aDeepArchitecture with multiple levels of representations. The achieved final representation is a highly non-linear function of the input data.

These are some basic concepts of learning deep learning and for for futher information on deep learning log on to wikipedia or other available sources...